Text autoencoders are commonly used for conditional generation tasks such as style transfer. We propose methods which are plug and play, where any pretrained autoencoder can be used, and only require learning a mapping within the autoencoder's embedding space, training embedding-to-embedding (Emb2Emb). This reduces the need for labeled training data for the task and makes the training procedure more efficient. Crucial to the success of this method is a loss term for keeping the mapped embedding on the manifold of the autoencoder and a mapping which is trained to navigate the manifold by learning offset vectors. Evaluations on style transfer tasks both with and without sequence-to-sequence supervision show that our method performs better than or comparable to strong baselines while being up to four times faster.

In "The Code Detectives," two middle school girls who love coding use artificial intelligence to solve mysteries. For 17-year-old author Ria Dosha, writing the book series is a way to advocate for increasing diversity within the technology field. "I've brought a diverse cast of characters to life, with the series centering around Ramona Diaz, a powerful young girl of color," says Ria, a student at Cupertino's Monta Vista High School. "The book series gives young girls strong, fictional role models in technology and AI, and introduces them to AI topics in a compelling way, clearing common misconceptions." Ria writes what shoe knows, and vice versa.

Every day, dozens of like-minded mathematicians gather on an online forum called Zulip to build what they believe is the future of their field. Original story reprinted with permission from Quanta Magazine, an editorially independent publication of the Simons Foundation whose mission is to enhance public understanding of science by covering research develop ments and trends in mathe matics and the physical and life sciences. They're all devotees of a software program called Lean. It's a "proof assistant" that, in principle, can help mathematicians write proofs. But before Lean can do that, mathematicians themselves have to manually input mathematics into the program, translating thousands of years of accumulated knowledge into a form Lean can understand.

Python is the most used language in machine learning. Engineers writing machine learning systems often use Jupyter Notebooks and Python together. Jupyter Notebooks is a web application that allows experimentation by creating and sharing documents that contain live code, equations, and more. Machine learning involves trial and error to see which hyperparameters and feature engineering choices work best. It's useful to have a development environment such as Python so that you don't need to compile and package code before running it each time.

AI (Artificial Intelligence) governance is about evaluating and monitoring algorithms for effectiveness, risk, bias and ROI (Return On Investment). But there is a problem: Often not enough attention is paid to this part of the AI process. "AI projects are rarely coordinated across a company and data science teams are often isolated from application development," said Mike Beckley, who is the CTO of Appian. "And now regulators are starting to ask questions businesses don't now how to answer." Keep in mind that AI introduces unique problems.

In this paper, we investigate the following two limitations for the existing distractor generation (DG) methods. First, the quality of the existing DG methods are still far from practical use. There is still room for DG quality improvement. Second, the existing DG designs are mainly for single distractor generation. However, for practical MCQ preparation, multiple distractors are desired. Aiming at these goals, in this paper, we present a new distractor generation scheme with multi-tasking and negative answer training strategies for effectively generating \textit{multiple} distractors. The experimental results show that (1) our model advances the state-of-the-art result from 28.65 to 39.81 (BLEU 1 score) and (2) the generated multiple distractors are diverse and show strong distracting power for multiple choice question.

Finite Mixture Regression (FMR) refers to the mixture modeling scheme which learns multiple regression models from the training data set. Each of them is in charge of a subset. FMR is an effective scheme for handling sample heterogeneity, where a single regression model is not enough for capturing the complexities of the conditional distribution of the observed samples given the features. In this paper, we propose an FMR model that 1) finds sample clusters and jointly models multiple incomplete mixed-type targets simultaneously, 2) achieves shared feature selection among tasks and cluster components, and 3) detects anomaly tasks or clustered structure among tasks, and accommodates outlier samples. We provide non-asymptotic oracle performance bounds for our model under a high-dimensional learning framework. The proposed model is evaluated on both synthetic and real-world data sets. The results show that our model can achieve state-of-the-art performance.

AI (Artificial Intelligence) governance is about evaluating and monitoring algorithms for effectiveness, risk, bias and ROI (Return On Investment). But there is a problem: Often not enough attention is paid to this part of the AI process. "AI projects are rarely coordinated across a company and data science teams are often isolated from application development," said Mike Beckley, who is the CTO of Appian. "And now regulators are starting to ask questions businesses don't now how to answer." Keep in mind that AI introduces unique problems.

This story appeared in the November 2020 issue as "Cracking the 414s." In the 1983 techno-thriller WarGames, David Lightman, played by a fresh-faced Matthew Broderick, sits in his bedroom, plunking away on a boxy computer using an 8-bit Intel processor. As text flashes across the screen, David's face lights up; he believes he's hacking into a video game company, but the unwitting teenager is actually facing off against a military supercomputer. "Shall we play a game?" the computer asks ominously. In the film, the subsequent showdown triggers a countdown to World War III.

While I was making dinner, I yelled at Alexa. But the recipe was a little complicated, and I kept having to repeat myself to get the damn Amazon Echo to turn off the timer. And when I used my computer communication voice to ask it to play NPR One so I could catch up on the news--it had been a whole eight or nine minutes since I had checked in with the world--it tried three times to instead play "The Austin 100: A SXSW Mix From NPR Music." I feel a little bad about it, remembering Rachel Withers' (very persuasive!) 2018 piece for Future Tense about why she won't date men who are rude to Alexa: It matters how you interact with your virtual assistant, not because it has feelings or will one day murder you in your sleep for disrespecting it, but because of how it reflects on you. Alexa is not human, but we engage with her like one.